| text-embedding-3-small | azure | azure | – | 0.0200n/a | freen/a | 0.0150n/a | –n/a | –n/a | –n/a | –n/a | 8191 | – | – | aggregator | modelsdev |
| text-embedding-3-small | azure | openai | – | 0.0200n/a | freen/a | 0.0150n/a | –n/a | –n/a | –n/a | –n/a | 8191 | – | – | aggregator | modelsdev |
| flux-2-dev | together | together | – | –n/a | 0.0154n/a | 0.0154n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| llama3.2-11b-vision-instruct | meta | lambda | – | 0.0150n/a | 0.0250n/a | 0.0175n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| llama3.2-3b-instruct | meta | lambda | – | 0.0150n/a | 0.0250n/a | 0.0175n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| bytedance-seedream-3-0 | together | together | – | 0.0180n/a | –n/a | 0.0180n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| Llama 3.2 3B Instruct | openrouter | deepinfra | – | 0.02000.0060 | 0.02000.0060 | 0.02000.0060 | –n/a | –n/a | –n/a | –n/a | 32768 | llama3 | 2025-10-04 ↑ | aggregator | litellm |
| PaddleOCR-VL | novita | novita | – | 0.0200n/a | 0.0200n/a | 0.0200n/a | –n/a | –n/a | –n/a | –n/a | 16384 | – | 2026-01-13 ↓ | aggregator | litellm |
| Meta: Llama 3.2 1B Instruct | openrouter | novita | – | 0.02000.0060 | 0.02000.0060 | 0.02000.0060 | –n/a | –n/a | –n/a | –n/a | 60000 | llama3 | – | aggregator | litellm |
| Qwen/Qwen2-1.5B-Instruct | alibaba | together | – | 0.0200n/a | 0.0200n/a | 0.0200n/a | –n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | litellm |
| google-imagen-4-0-fast | together | together | – | 0.0200n/a | –n/a | 0.0200n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| Mistral Nemo | openrouter | dekallm | fp8 | 0.01800.0064 | 0.03000.0107 | 0.02100.0075 | –n/a | –n/a | –n/a | –n/a | 60288 | mistral | – | api | openrouter |
| Mistral Nemo | openrouter | openrouter | – | 0.01900.0068 | 0.03000.0107 | 0.02180.0077 | –n/a | –n/a | –n/a | –n/a | 60288 | mistral | – | api | openrouter |
| Mistral Nemo | openrouter | deepinfra | fp8 | 0.01900.0068 | 0.03000.0107 | 0.02180.0077 | –n/a | –n/a | –n/a | –n/a | 60288 | mistral | – | api | openrouter |
| mistralai/Mistral-Nemo-Instruct-2407 | mistral | deepinfra | – | 0.0190n/a | 0.0300n/a | 0.0218n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | 2026-08-27 ↓ | aggregator | litellm |
| Mistral-Nemo-Instruct-2407 | deepinfra | deepinfra | – | 0.0190n/a | 0.0300n/a | 0.0218n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-deepinfra |
| Llama 3.1 8B Instruct | openrouter | deepinfra | fp8 | 0.02000.0060 | 0.04000.0120 | 0.02500.0075 | –n/a | –n/a | –n/a | –n/a | 16384 | llama3 | – | api | openrouter |
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | meta | deepinfra | – | 0.0200n/a | 0.0400n/a | 0.0250n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | 2026-08-27 ↑ | aggregator | litellm |
| Meta-Llama-3.1-8B-Instruct-Turbo | deepinfra | deepinfra | – | 0.0200n/a | 0.0400n/a | 0.0250n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-deepinfra |
| Llama 3.1 8B Instruct | openrouter | novita | fp8 | 0.02000.0060 | 0.05000.0150 | 0.02750.0083 | –n/a | –n/a | –n/a | –n/a | 16384 | llama3 | – | api | openrouter |
| Llama 3.1 8B Instruct | openrouter | novita | – | 0.02000.0060 | 0.05000.0150 | 0.02750.0083 | –n/a | –n/a | –n/a | –n/a | 16384 | llama3 | 2026-01-13 ↓ | aggregator | litellm |
| hermes3-8b | lambda | lambda | – | 0.0250n/a | 0.0400n/a | 0.0288n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| lfm-7b | lambda | lambda | – | 0.0250n/a | 0.0400n/a | 0.0288n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| llama3.1-8b-instruct | meta | lambda | – | 0.0250n/a | 0.0400n/a | 0.0288n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| Mistral Nemo | openrouter | parasail | fp8 | 0.03000.0107 | 0.03000.0107 | 0.03000.0107 | –n/a | –n/a | –n/a | –n/a | 60288 | mistral | – | api | openrouter |
| Llama Prompt Guard 2 22M | meta | groq | – | 0.0300n/a | 0.0300n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | 512 | – | – | aggregator | litellm |
| meta-llama/Llama-Guard-3-8B | meta | nebius | – | 0.0200n/a | 0.0600n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| meta-llama/Meta-Llama-3.1-8B-Instruct | meta | nebius | – | 0.0200n/a | 0.0600n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| Qwen/Qwen2-VL-7B-Instruct | alibaba | nebius | – | 0.0200n/a | 0.0600n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| DeepSeek-OCR | deepseek | novita | – | 0.0300n/a | 0.0300n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | 8192 | – | 2026-01-13 ↓ | aggregator | litellm |
| Qwen3 4B | alibaba | novita | – | 0.0300n/a | 0.0300n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | 2026-01-13 ↓ | aggregator | litellm |
| deepseek/deepseek-ocr-2 | deepseek | novita | – | 0.0300n/a | 0.0300n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | 8192 | – | – | aggregator | litellm |
| wan-2-6-image | together | together | – | –n/a | 0.0300n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| flux-2-pro | together | together | – | –n/a | 0.0300n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| flux-2-flex | together | together | – | –n/a | 0.0300n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| bytedance-seedream-4-0 | together | together | – | 0.0300n/a | –n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| GLM-OCR | zhipu | zhipu | – | 0.0300n/a | 0.0300n/a | 0.0300n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-zhipu |
| inclusionAI: Ling 3.0 Flash VL | openrouter | openrouter | – | 0.0210n/a | 0.0616n/a | 0.0312n/a | 0.0042n/a | –n/a | –n/a | –n/a | 262144 | – | – | api | openrouter |
| inclusionAI: Ling 3.0 Flash VL | openrouter | novita | – | 0.0210n/a | 0.0616n/a | 0.0312n/a | 0.0042n/a | –n/a | –n/a | –n/a | 262144 | – | – | api | openrouter |
| inclusionAI: Ling 3.0 Flash | openrouter | openrouter | – | 0.0210n/a | 0.0630n/a | 0.0315n/a | 0.0042n/a | –n/a | –n/a | –n/a | 262144 | – | – | api | openrouter |
| inclusionAI: Ling 3.0 Flash | openrouter | novita | unknown | 0.0210n/a | 0.0630n/a | 0.0315n/a | 0.0042n/a | –n/a | –n/a | –n/a | 262144 | – | – | api | openrouter |
| inclusionAI: Ling 3.0 Flash | openrouter | novita | – | 0.0210n/a | 0.0630n/a | 0.0315n/a | 0.0042n/a | –n/a | –n/a | –n/a | 262144 | – | – | api | openrouter |
| together/Tev1-4B-experimental | together | together | – | 0.0420n/a | freen/a | 0.0315n/a | 0.0420n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | litellm |
| Qwen3-ASR Flash | alibaba | alibaba | – | 0.0320n/a | 0.0320n/a | 0.0320n/a | –n/a | –n/a | –n/a | –n/a | 53248 | – | 2026-10-04 ↓ | aggregator | modelsdev |
| gpt-image-1-5 | together | together | – | –n/a | 0.0340n/a | 0.0340n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | official | official-together |
| DeepSeek-V4-Flash | openrouter | streamlake | fp8 | 0.02800.0092 | 0.05600.0184 | 0.03500.0115 | 0.00560.0018 | –n/a | –n/a | –n/a | 1048576 | deepseek | – | api | openrouter |
| meta-llama/Meta-Llama-3.1-8B-Instruct | meta | deepinfra | – | 0.0300n/a | 0.0500n/a | 0.0350n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| Llama 3.2 3B Instruct | openrouter | novita | – | 0.03000.0090 | 0.05000.0150 | 0.03500.0105 | –n/a | –n/a | –n/a | –n/a | 32768 | llama3 | 2026-01-13 ↓ | aggregator | litellm |
| gpt-oss-20b (GovCloud) | openrouter | openrouter | – | 0.01800.0051 | 0.09000.0254 | 0.03600.0101 | 0.00900.0025 | –n/a | 0.02400.0068 | 0.110.0316 | 131072 | o200k | – | api | openrouter |
| gpt-oss-20b (GovCloud) | openrouter | darkbloom | fp8 | 0.01800.0051 | 0.09000.0254 | 0.03600.0101 | 0.00900.0025 | –n/a | –n/a | –n/a | 131072 | o200k | – | api | openrouter |